© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60946
    Prev
    Next
    INDEX
    Explanations

    themes related to judgment and critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     voks
    -0.08
    ansa
    -0.08
     DevComponents
    -0.08
    ãĤ¦ãĥĪ
    -0.08
    جÙĪ
    -0.07
    mailbox
    -0.07
    actionDate
    -0.07
    698
    -0.07
     ("-
    -0.07
    RefCount
    -0.07
    POSITIVE LOGITS
    ;
    0.07
     :
    0.06
     prefix
    0.06
    ials
    0.06
     ;
    0.06
     definitely
    0.06
    :
    0.06
     ar
    0.06
     incident
    0.06
     t
    0.06
    Activations Density 0.063%

    No Known Activations